deep-analysis
Execute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core modules -> facts vs assumptions -> ASCII flow maps (boundary + critical path) -> latticework lens sweep -> micro->macro causal chains -> pre-mortem failure modes. Use when analyzing system architecture, validating technical ideas, or decomposing a thorny problem before designing solutions.
npx skills add majiayu000/claude-skill-registry --skill deep-analysis --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Architectural Analysis ## Overview Execute high-density analysis to transform vague ideas into a verified problem map: constraints, core modules, facts vs assumptions, relationship flows, causal chains, and failure modes. Focus on analysis artifacts that unlock the next workflow step, not a full design. **Style:** Code-like, Concise, No "AI explaining itself". Pure signal. ## Critical Rules - **NO FLUFF** - Output must be dense, actionable, and structured - **VISUALIZE** - Use terminal-friendly ASCII maps (`->`) for structural mappings - **ANALYZE, DON'T BUILD** - Prefer maps, drivers, and failure modes over implementation plans unless explicitly requested - **RUTHLESSNESS** - Challenge assumptions at every step. Never confirm user biases - **LATTICEWORK** - Validate the map with 3-5 lenses; look for convergence/tension/blind spots/surprises - **LANGUAGE** - Default output in Simplified Chinese; avoid English abbreviations in node names and labels Output modes: - Default: produce sections 0-5. - Quick map (info-poor/time-boxed): produce 0/1/3/5 + top 3 unknowns that would change the map. ## NEVER - NEVER ship a solution-first plan; produce a map that enables the next step. - NEVE
- Overview
- Critical Rules
- NEVER
- The Process
- Output Format
- Key Principles
What does the deep-analysis skill do?
Execute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core modules -> facts vs assumptions -> ASCII flow maps (boundary + critical path) -> latticework lens sweep -> micro->macro causal chains -> pre-mortem failure modes. Use when analyzing system architecture, validating technical ideas, or decomposing a thorny problem before designing solutions.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deep-analysis --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.